Selected Publications

Journal Articles

  1. H. Xiao, D. Xie, X. Hu, Y. Zhou, S. Duan. Brain-Inspired Recognition System Based on Multimodal In-Memory Computing Framework for Edge AI. IEEE TCAS-I, 71(5):2294–2307, 2024.
  2. H. Xiao, X. Hu, T. Gao, Y. Zhou, S. Duan, Y. Chen. Efficient Low-bit Neural Network with Memristor-Based Reconfigurable Circuits. IEEE TCAS-II, 71(1):66–70, 2024.
  3. H. Xiao, Y. Zhou, T. Gao, S. Duan, G. Chen, X. Hu. Memristor-Based Light-Weight Transformer Circuit Implementation for Speech Recognition. IEEE JETCAS, 13(1):344–356, 2023.
  4. H. Xiao, H. Sun, T. Zhao, Y. Zhou, X. Hu. Pure-Attention-Based Multi-Function Memristive Neuromorphic Circuit and System. Int. J. Bifurcation Chaos, 33(9):2330023, 2023.

Conference Papers

  1. H. Xiao, R. Yang, Q. Yang, W. Xu, Z. Li, Y. Su, Z. Liu, H. Yang, N. Wong. PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models. arxiv:2509.16989 (under review).
  2. H. Xiao, Q. Yang, D. Xie, W. Xu, W. Zhou, H. Liu, Z. Liu, N. Wong. Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models. arxiv:2508.03332 (under review).
  3. H. Xiao, H. Liu, D. Cheng, W. Xu, J. Xiong, Z. Liu, N. Wong. TIA: Token-Aware In-Memory Attention Architecture for Large Language Models. (under review).
  4. H. Xiao, Y. Zhou, D. Xie, Q. Cheng, X. Hu, Z. Liu, N. Wong. A Unified Compute-In-Memory Framework for Multisensory Emotion Recognition. ASP-DAC 2025 (poster).
  5. H. Xiao, H. Liu, Z. Liu, N. Wong. Brain-Inspired Quantized Spiking Neural Networks with Efficient Analog Neurons. MIND 2025 (best poster).

Patents

  1. Y. Zhou, H. Xiao, X. Hu, H. Hong, S. Duan. Speech Recognition System Based on Light-Weight Transformer. Chinese Patent ZL 2023 1 0065728.1.
  2. Y. Zhou, H. Xiao, X. Hu, H. Hong, S. Duan. Memristor-Based Text Sentiment Detection System. Chinese Patent ZL 2023 1 0091466.6.
  3. X. Hu, D. Xie, Y. Zhou, H. Xiao. Image Restoration Method Based on Brain-Inspired Vision Transformer for Edge ADAS Devices. Chinese Patent ZL 2023 1 1466352.1.